基于单幅图像的视线计算研究

提出了一种新的基于单幅眼睛图像的视线计算方法。通过假定两眼的视线向量以及左右虹膜中心点组成的向量共面,可以计算得到两眼的视线方向。与现有的三维视线计算方法相比,提出的视线计算方法不需要眼角坐标等脸部特征信息,另外也不需要已知相机的焦距大小。可以允许相机的焦距大小以及与用户的距离自由改变。最后实验的结果也比较理想,充分证明了提出的视线计算方法的可行性。     

使用人眼几何特征的视线追踪方法

目的 视线追踪是人机交互的辅助系统,针对传统的虹膜定位方法误判率高且耗时较长的问题,本文提出了一种基于人眼几何特征的视线追踪方法,以提高在2维环境下视线追踪的准确率。方法 首先通过人脸定位算法定位人脸位置,使用人脸特征点检测的特征点定位眼角点位置,通过眼角点计算出人眼的位置。直接使用虹膜中心定位算法的耗时较长,为了使虹膜中心定位的速度加快,先利用虹膜图片建立虹膜模板,然后利用虹膜模板检测出虹膜区域的位置,通过虹膜中心精定位算法定位虹膜中心的位置,最后提取出眼角点、虹膜中心点等信息,对点中包含的角度信息、距离信息进行提取,组合成眼动向量特征。使用神经网络模型进行分类,建立注视点映射关系,实现视线的追踪。通过图像的预处理对图像进行增强,之后提取到了相对的虹膜中心。提取到需要的特征点,建立相对稳定的几何特征代表眼动特征。结果 在普通的实验光照环境中,头部姿态固定的情况下,识别率最高达到98.9%,平均识别率达到95.74%。而当头部姿态在限制区域内发生变化时,仍能保持较高的识别率,平均识别率达到了90%以上。通过实验分析发现,在头部变化的限制区域内,本文方法具有良好的鲁棒性。结论 本文提出使用模板匹配与虹膜精定位相结合的方法来快速定位虹膜中心,利用神经网络来对视线落点进行映射,计算视线落点区域,实验证明本文方法具有较高的精度。     

虹膜清晰程度与人眼拍摄距离对应关系研究*

现有的虹膜识别仪通常要求人眼在较小的范围内成像,许多被测试者由于需要反复调整位置才能满足虹膜图像的采集要求而感到心烦,如果能够给出人眼的拍摄范围,将方便用户的使用。研究并建立在人眼偏离镜头聚焦位置的情况下,所拍摄虹膜图像清晰程度与人眼到镜头之间拍摄距离的对应关系,选择并通过实验评价了用于表述图像清晰程度与拍摄距离对应关系的四种评价函数的性能。实验结果表明：当人眼在90150 mm内移动时,所拍摄的虹膜图像清晰程度先逐步增大,到达峰值后,再逐步减小;当人眼与摄像机之间的最大可拍摄范围为106132 mm时,     

基于运动方向的视角无关行为识别方法

针对人体运动方向的随机特性,研究场景中有多台摄像机时视角无关的行为识别方法。利用一台位置固定的摄像机,根据视频序列中运动目标质心空间坐标变化,确定其运动大致方向。根据该方向,选择具有垂直和平行运动轨迹方向视角的相机获得的序列图像,进行行为分析。提取人体运动行为侧像和正像轮廓的关键姿态建立特征库。应用单个相机平行线约束,通过转换因子由图像坐标恢复运动目标关键点的三维坐标,从而确定目标运动方向。建立室内多视角行为视频样本库,实验结果表明,利用该方法识别室内运动行为,能够达到视角无关行为识别的目的。     

Visual Focus of Attention in Non-calibrated Environments using Gaze Estimation

Estimating the focus of attention of a person highly depends on her/his gaze directionality. Here, we propose a new method for estimating visual focus of attention using head rotation, as well as fuzzy fusion of head rotation and eye gaze estimates, in a fully automatic manner, without the need for any special hardware or a priori knowledge regarding the user, the environment or the setup. Instead, we propose a system aimed at functioning under unpretending conditions, only with the usage of simple hardware, like a normal web-camera. Our system is aimed at functioning in a human-computer interaction environment, considering a person is facing a monitor with a camera adjusted on top. To this aim, we propose in this paper two novel techniques, based on local and appearance information, estimating head rotation, and we adaptively fuse them in a common framework. The system is able to recognize head rotational movement, under translational movements of the user towards any direction, without any knowledge or a-priori estimate of the user’s distance from the camera or camera intrinsic parameters.     

Developing Iris Recognition System for Smartphone Security

Smartphones have become an important way to store sensitive information; therefore, users’ privacy needs to be highly protected. This can be done by using the most reliable and accurate biometric identification system available today: iris recognition. This paper develops and tests an iris recognition system for smartphones. The system uses eye images that rely on visible wavelength; these images are acquired by the smartphone built-in camera. The development of the system passes through four main phases: the first phase is the iris segmentation phase, which is done in three steps to detect the iris region from the captured image, which contains the eye and part of the face using Haar Cascade Classifier training, pupil localization, and iris localization using a Circular Hough Transform. In the second phase, the system applies normalization using a Rubber Sheet model, which converts the iris image to a fixed size pattern. In the third phase, unique features are extracted from that pattern using a Deep Sparse Filtering algorithm. Finally, in the matching phase, seven different matching techniques are investigated to decide the most appropriate one the system will use to verify the user. Two types of testing are conducted: Offline and Online tests. The BIPLab database and a collected dataset are used to measure the accuracy of the system phases and to calculate the Equal Error Rate (EER) for the whole system. The average EER is 0.18 for the BIPLab database and 0.26 for the collected dataset.     

Head Movement Based Interaction in Mobility

The touchless techniques in human computer interaction (HCI) can effectively expand communication capabilities. In the paper we present the innovative touchless computer control method based on head movement analysis. The aim of our work was to replace the standard mouse with the movements of the user’s head. In contrast to the known solutions, our proposition does not require image recording of the user’s head and complex image analysis. The analysis of position in our solution is made using the camera worn by the user on the head. A project of such a solution has been developed and the research of it has been carried out. It has been shown that in this way it is possible to effectively move the screen cursor to the position which is identified by the user’s face orientation. Additionally, in this solution, the eye image analysis has been performed. Interpretation of blinking allowed executing system commands. Using the built prototype the experiments have been carried out in a group of 30 people. Studies have shown high efficiency and ergonomics of the proposed solution.     

一种高精度的虹膜识别算法的实现

该文提出了一种高精度的基于虹膜的身份识别的方法。该方法包括虹膜图像的预处理、虹膜的特征提取和虹膜的匹配与识别三个部分。虹膜图像的预处理包括虹膜图像的定位、归一化、增强和去噪。利用虹膜图像提供的丰富的纹理信息,特征提取采用Daubechies-2小波变换的纹理分析方法。匹配采用k近邻分类器。该算法对光照和噪声不敏感,且具有平移、缩放、旋转不变性。由实验结果表明,本文提出的方法提高了虹膜识别的有效性和准确性,是一种实用的身份识别方法。     

Ocular recognition databases and competitions: a survey

The use of the iris and periocular region as biometric traits has been extensively investigated, mainly due to the singularity of the iris features and the use of the periocular region when the image resolution is not sufficient to extract iris information. In addition to providing information about an individual’s identity, features extracted from these traits can also be explored to obtain other information such as the individual’s gender, the influence of drug use, the use of contact lenses, spoofing, among others. This work presents a survey of the databases created for ocular recognition, detailing their protocols and how their images were acquired. We also describe and discuss the most popular ocular recognition competitions (contests), highlighting the submitted algorithms that achieved the best results using only iris trait and also fusing iris and periocular region information. Finally, we describe some relevant works applying deep learning techniques to ocular recognition and point out new challenges and future directions. Considering that there are a large number of ocular databases, and each one is usually designed for a specific problem, we believe this survey can provide a broad overview of the challenges in ocular biometrics.

     

Enhanced near-infrared periocular recognition through collaborative rendering of hand crafted and deep features

Periocular recognition leverage from larger feature region and lesser user cooperation, when compared against the traditional iris recognition. Moreover, in the current scenario of Covid-19, where majority of people cover their faces with masks, potential of recognizing faces gets reduced by a large extent, calling for wide applicability of periocular recognition. In view of these facts, this paper targets towards enhanced representation of near-infrared periocular images, by combined use of hand-crafted and deep features. The hand-crafted features are extracted through partitioning of periocular image followed by obtaining the local statistical properties pertaining to each partition. Whereas, deep features are extracted through the popular convolutional neural network (CNN) ResNet-101 model. The extensive set of experiments performed with a benchmark periocular database validates the promising performance of the proposed method. Additionally, investigation of cross-spectral matching framework and comparison with state-of-the-art, reveal that combination of both types of features employed could prove to be extremely effective.

     

Ocular biometrics in the visible spectrum: A survey

Ocular biometrics encompasses the imaging and use of characteristic features extracted from the eyes for personal recognition. Ocular biometric modalities in visible light have mainly focused on iris, blood vessel structures over the white of the eye (mostly due to conjunctival and episcleral layers), and periocular region around eye. Most of the existing studies on iris recognition use the near infrared spectrum. However, conjunctival vasculature and periocular regions are imaged in the visible spectrum. Iris recognition in the visible spectrum is possible for light color irides or by utilizing special illumination. Ocular recognition in the visible spectrum is an important research area due to factors such as recognition at a distance, suitability for recognition with regular RGB cameras, and adaptability to mobile devices. Further these ocular modalities can be obtained from a single RGB eye image, and then fused together for enhanced performance of the system. Despite these advantages, the state-of-the-art related to ocular biometrics in visible spectrum is not well known. This paper surveys this topic in terms of computational image enhancement, feature extraction, classification schemes and designed hardware-based acquisition set-ups. Future research directions are also enumerated to identify the path forward.     

一种基于小波包分解的虹膜防伪检测方法

虹膜识别系统易受到伪虹膜的攻击,包括利用打印在隐形眼镜、玻璃眼或其他材料上的假虹膜纹理进行的攻击,所以检测出假虹膜的防伪算法至关重要。为此,提出一种利用小波包分解进行特征提取的虹膜防伪检测方法。首先对目标图像进行二级小波包分解,然后计算各子带图像的熵,最后将各子带图像的熵值之和作为提取的特征值。实验在包含500幅虹膜图像的数据库中进行,结果表明此方法可以有效地将真假虹膜区分开来。     

Iris segmentation in non-ideal images using graph cuts

A non-ideal iris image segmentation approach based on graph cuts is presented that uses both the appearance and eye geometry information. A texture measure based on gradients is computed to discriminate between eyelash and non-eyelash regions, combined with image intensity differences between the iris, pupil, and the background (region surrounding the iris) are utilized as cues for segmentation. The texture and intensity distributions for the various regions are learned from histogramming and explicit sampling of the pixels estimated to belong to the corresponding regions. The image is modeled as a Markov Random Field and the energy minimization is achieved via graph cuts to assign each image pixel one of the four possible labels: iris, pupil, background, and eyelash. Furthermore, the iris region is modeled as an ellipse, and the best fitting ellipse to the initial pixel based iris segmentation is computed to further refine the segmented region. As a result, the iris region mask and the parameterized iris shape form the outputs of the proposed approach that allow subsequent iris recognition steps to be performed for the segmented irises. The algorithm is unsupervised and can deal with non-ideality in the iris images due to out-of-plane rotation of the eye, iris occlusion by the eyelids and the eyelashes, multi-modal iris grayscale intensity distribution, and various illumination effects. The proposed segmentation approach is tested on several publicly available non-ideal near infra red (NIR) iris image databases. We compare both the segmentation error and the resulting recognition error with several leading techniques, demonstrating significantly improved results with the proposed technique.     

A method of reactive zoom control from uncertainty in tracking

The tuning of a constant velocity Kalman filter, used for tracking by a camera fitted with a variable focal-length lens, is shown to be preserved under a scale change in process noise if accompanied by an inverse scaling in the focal length, provided the image measurement error is of fixed size in image coordinates. Based on this observation, a practical method of zoom control has been built by setting an upper limit on the probability that the innovation (and hence fixation error) exceeds the image half-width. The innovation covariance matrix used to determine the innovation limit is derived over two timescales, which enables a rapid zooming out response and slower zooming in. Experimental simulations are presented, before results are given from a video-rate implementation using a camera with two motorized orientation axes and fitted with a computer-controlled zoom lens. The delays in the feedback loops, comprising image capture delay, platform response lag and zoom lens response lag, are carefully calibrated by fitting to their frequency responses. It is found that the cumulative uncertainty in delay gives rise to an image error which is part constant and part proportional to focal length, resulting in a beneficial adaptation of the filter.     

A model for smooth viewing and navigation of large 2D information spaces

Large 2D information spaces, such as maps, images, or abstract visualizations, require views at various level of detail: close ups to inspect details, overviews to maintain (literally) an overview. Users often change their view during a session. Smooth animations enable the user to maintain an overview during interactive viewing and to understand the context of separate views. We present a generic model to handle smooth image viewing. The core of the model is a metric on the effect of simultaneous zooming and panning, based on an estimate of the perceived velocity. Using this metric, solutions for various problems are derived, such as the optimal animation between two views, automatic zooming, and the parametrization of arbitrary camera paths. Optimal is defined here as smooth and efficient. Solutions are based on the shortest paths of a virtual camera, given the metric. The model has two free parameters: animation speed and zoom/pan trade off. A user experiment to find good values for these is described. Finally, it is shown how the model can be extended to deal also with rotation and nonuniform scaling.     

Effect of viewing a three-dimensional movie with vertical parallax

The vertical parallax of both eyes, caused by tilting the head when watching three-dimensional (3D) television or movies, can induce visual fatigue or visually-induced motion sickness. The purpose of the present study was to investigate levels of discomfort and fatigue and eye movements induced by viewing a 3D movie with vertical parallax. Two experiments were conducted to investigate the relationship between the degree of vertical parallax and the magnitude of the effect. The results indicate that the viewer’s feeling of visual malaise increases as the angle of the screen increases, with respect to the observer’s head, because eye movement does not compensate for the parallax in the vertical direction. Binocular rivalry is believed to occur when viewing a 3D movie with vertical parallax, which may induce even more visual malaise.     

基于结构特征的视网膜血管形态识别

针对视网膜眼底图像获取过程中眼球转动的问题,提出一种基于节点最近邻结构的具有旋转和平移不变性的视网膜血管形态识别方法.该方法利用节点的周边结构稳定性的特点来进行节点结构特征提取,进行图像相关结构匹配的判定.实验结果表明了该识别算法的有效性和可靠性,且不需要进行方位对准处理,具有较好地识别灵活性和实用性,正确识别率达到98.57％.     

Reactive control of zoom while fixating using perspective and affine cameras

This paper describes reactive visual methods of controlling the zoom setting of the lens of an active camera while fixating upon an object. The first method assumes a perspective projection and adjusts zoom to preserve the ratio of focal length to scene depth. The active camera is constrained to rotate, permitting self-calibration from the image motion of points on the static background. A planar structure from motion algorithm is used to recover the depth of the foreground. The foreground-background segmentation exploits the properties of the two different interimage homographies which are observed. The fixation point is updated by transfer via the observed planar structure. The planar method is shown to work on real imagery, but results from simulated data suggest that its extension to general 3D structure is problematical under realistic viewing and noise regimes. The second method assumes an affine projection. It requires no self-calibration and the zooming camera may move generally. Fixation is again updated using transfer, but now via the affine structure recovered by factorization. Analysis of the projection matrices allows the relative scale of the affine bases in different views to be found in a number of ways and, hence, controlled to unity. The various ways are compared and the best used on real imagery captured from an active camera fitted with a controllable zoom lens in both look-move and continuous operation.     

Head mouse control system for people with disabilities

In this paper, a human–machine interface for disabled people with spinal cord injuries is proposed. The designed human–machine interface is an assistive system that uses head movements and blinking for mouse control. In the proposed system, by moving one's head, the user moves the mouse pointer to the required coordinates and then blinks to send commands. The considered head mouse control is based on image processing including facial recognition, in particular, the recognition of the eyes, mouth, and nose. The proposed recognition system is based on the convolutional neural network, which uses the low-quality images that are captured by a computer's camera. The convolutional neural network (CNN) includes convolutional layers, a pooling layer, and a fully connected network. The CNN transforms the head movements to the actual coordinates of the mouse. The designed system allows people with disabilities to control a mouse pointer with head movements and to control mouse buttons with blinks. The results of the experiments demonstrate that this system is robust and accurate. This invention allows people with disabilities to freely control mouse cursors and mouse buttons without wearing any equipment.     

Iris recognition using shape-guided approach and game theory

Most state-of-the-art iris recognition algorithms claim to perform with a very high recognition accuracy in a strictly controlled environment. However, their recognition accuracies significantly decrease when the acquired images are affected by different noise factors including motion blur, camera diffusion, head movement, gaze direction, camera angle, reflections, contrast, luminosity, eyelid and eyelash occlusions, and problems due to contraction and dilation. The novelty of this research effort is that we propose to apply a variational model to localize the iris region belonging to given shape space using active contour method, a geometric shape prior, and the Mumford–Shah functional. This variational model is robust against noise, poor localization and weak iris/sclera boundaries. Furthermore, we apply the Modified Contribution-Selection Algorithm (MCSA) for iris feature ranking based on the Multi-Perturbation Shapley Analysis (MSA), a framework which relies on cooperative game theory to estimate the effectiveness of the features iteratively and select them accordingly, using either forward selection or backward elimination approaches. The verification and identification performance of the proposed scheme is validated using the ICE 2005, the UBIRIS Version 1, the CASIA Version 3 Interval, and WVU Nonideal datasets.